160 citations · 317 across the 55 of their papers we have counts for
10 papers · 1 filter
Classifying and Addressing the Diversity of Errors in Retrieval-Augmented Generation Systems
Kin Kwan Leung, Mouloud Belbahri, Yi Sui +4
Retrieval-augmented generation (RAG) is a prevalent approach for building LLM-based question-answering systems that can take advantage of external knowledge databases. Due to the c…
Self-Supervised Representation Learning as Mutual Information Maximization
Akhlaqur Rahman Sabby, Yi Sui, Tongzi Wu +2
Self-supervised representation learning (SSRL) has demonstrated remarkable empirical success, yet its underlying principles remain insufficiently understood. While recent works att…
MaskSQL: Safeguarding Privacy for LLM-Based Text-to-SQL via Abstraction
Sepideh Abedini, Shubhankar Mohapatra, D. B. Emerson +3
Large language models (LLMs) have shown promising performance on tasks that require reasoning, such as text-to-SQL, code generation, and debugging. However, regulatory frameworks w…
Document Summarization with Conformal Importance Guarantees
Bruce Kuwahara, Chen-Yuan Lin, Xiao Shi Huang +5
Automatic summarization systems have advanced rapidly with large language models (LLMs), yet they still lack reliable guarantees on inclusion of critical content in high-stakes dom…
Response Quality Assessment for Retrieval-Augmented Generation via Conditional Conformal Factuality
Naihe Feng, Yi Sui, Shiyi Hou +2
Existing research on Retrieval-Augmented Generation (RAG) primarily focuses on improving overall question-answering accuracy, often overlooking the quality of sub-claims within gen…
Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems
Brendan Leigh Ross, Noël Vouitsis, Atiyeh Ashari Ghomi +8
Although large language models (LLMs) are becoming increasingly capable of solving challenging real-world tasks, accurately quantifying their uncertainty remains a critical open pr…
CausalPFN: Amortized Causal Effect Estimation via In-Context Learning
Vahid Balazadeh, Hamidreza Kamkari, Valentin Thomas +4
Causal effect estimation from observational data is fundamental across various applications. However, selecting an appropriate estimator from dozens of specialized methods demands…
Trustworthy AI Must Account for Interactions
Jesse C. Cresswell
Trustworthy AI encompasses many aspirational aspects for aligning AI systems with human values, including fairness, privacy, robustness, explainability, and uncertainty quantificat…
Zero-Execution Retrieval-Augmented Configuration Tuning of Spark Applications
Raunaq Suri, Ilan Gofman, Guangwei Yu +1
Large-scale data processing is increasingly done using distributed computing frameworks like Apache Spark, which have a considerable number of configurable parameters that affect r…
DRESS: Disentangled Representation-based Self-Supervised Meta-Learning for Diverse Tasks
Wei Cui, Tongzi Wu, Jesse C. Cresswell +2
Meta-learning represents a strong class of approaches for solving few-shot learning tasks. Nonetheless, recent research suggests that simply pre-training a generic encoder can pote…